metadata

language:
  - ml
tags:
  - audio
  - automatic-speech-recognition
  - vegam
license: mit
datasets:
  - google/fleurs
  - thennal/IMaSC
  - mozilla-foundation/common_voice_11_0
library_name: ctranslate2

Note: Model file size is 3.06 GB

vegam-whipser-medium-ml (വേഗം)

This is a conversion of thennal/whisper-medium-ml to the CTranslate2 model format.

This model can be used in CTranslate2 or projects based on CTranslate2 such as faster-whisper.

Installation

Install faster-whisper. More details about installation can be found here in faster-whisper.

pip install faster-whisper

Install git-lfs for using this project. Other approaches for downloading git-lfs in non-debian based systems.

Note that git-lfs is just for downloading model from hugging-face.

apt-get install git-lfs

Download the model weights

git lfs install
git clone https://huggingface.co/kurianbenoy/vegam-whisper-medium-ml

Usage

from faster_whisper import WhisperModel

model_path = "vegam-whisper-medium-ml"

# Run on GPU with FP16
model = WhisperModel(model_path, device="cuda", compute_type="float16")

# or run on GPU with INT8
# model = WhisperModel(model_path, device="cuda", compute_type="int8_float16")
# or run on CPU with INT8
# model = WhisperModel(model_path, device="cpu", compute_type="int8")

segments, info = model.transcribe("audio.mp3", beam_size=5)

print("Detected language '%s' with probability %f" % (info.language, info.language_probability))

for segment in segments:
    print("[%.2fs -> %.2fs] %s" % (segment.start, segment.end, segment.text))

Example

from faster_whisper import WhisperModel

model_path = "vegam-whisper-medium-ml"

model = WhisperModel(model_path, device="cuda", compute_type="float16")


segments, info = model.transcribe("00b38e80-80b8-4f70-babf-566e848879fc.webm", beam_size=5)

print("Detected language '%s' with probability %f" % (info.language, info.language_probability))

for segment in segments:
    print("[%.2fs -> %.2fs] %s" % (segment.start, segment.end, segment.text))

Detected language 'ta' with probability 0.353516

[0.00s -> 4.74s] പാലം കടുക്കുവോളം നാരായണ പാലം കടന്നാലൊ കൂരായണ

Note: The audio file 00b38e80-80b8-4f70-babf-566e848879fc.webm is from Malayalam Speech Corpus and is stored along with model weights.

Conversion Details

This conversion was possible with wonderful CTranslate2 library leveraging the Transformers converter for OpenAI Whisper.The original model was converted with the following command:

ct2-transformers-converter --model thennal/whisper-medium-ml --output_dir vegam-whisper-medium-ml

Many Thanks to

Creators of CTranslate2 and faster-whisper
Thennal D K
Santhosh Thottingal